CtrlK
BlogDocsLog inGet started
Tessl Logo

add-cpu-op

Add a new operation to the OpenVINO CPU plugin — node registration, JIT/oneDNN executors (AVX2/AVX-512/AMX), and functional tests.

53

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/agents-prototype/skills/add-cpu-op/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is admirably concise and well-structured as an overview, but it delegates nearly all executable detail to step files that are not bundled, and lacks inter-step validation checkpoints. Ensuring the referenced files exist and adding verify gates would substantially improve actionability and workflow clarity.

Suggestions

Provide the referenced step1-analysis.md through step4-testing.md files in the skill bundle so the one-level-deep navigation resolves.

Add concrete inline guidance (e.g. the node-class skeleton, factory registration snippet, or test command) so SKILL.md is actionable even before opening the step files.

Insert explicit validation checkpoints between steps (e.g. 'build and run single-layer tests before moving to optimization') to close the workflow-clarity gap.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — a short 'When to use' paragraph plus a compact 4-row table with no padding or unnecessary explanation.

5 / 5

Actionability

Concrete executable guidance (code, commands, file formats) is offloaded entirely to the referenced stepN-*.md files, leaving only high-level purpose descriptions inline; the specific steps to execute are missing from SKILL.md itself.

2 / 5

Workflow Clarity

A clear ordered 4-step sequence is present with per-step artifacts, but there are no validation checkpoints between steps despite this being a code-generation workflow.

3 / 5

Progressive Disclosure

Structure is reasonable — a table linking to one-level-deep step files — but the referenced step1-4 markdown files are not present in any bundle directory, so the navigation points to missing materials.

3 / 5

Total

13

/

20

Passed

Description

62%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and clearly occupies a distinct niche, but it omits an explicit 'when to use' trigger clause and relies on technical jargon over natural user phrasing. Adding a 'Use when...' sentence with common trigger terms would lift the completeness and trigger_term_quality dimensions.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when implementing or extending CPU plugin support for a new OpenVINO op after the op spec is finalized.'

Add natural user-facing trigger terms (e.g. 'CPU op', 'add CPU operation', 'OpenVINO executor') alongside the technical jargon.

Optionally enumerate the concrete sub-actions (register node, write JIT/oneDNN executor, add single-layer tests) to push specificity toward 5.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'node registration, JIT/oneDNN executors (AVX2/AVX-512/AMX), and functional tests' — with ISA-level specifics; not a full 5 since it stops at three bundled actions rather than enumerating each sub-step.

4 / 5

Completeness

The 'what' is clear (add CPU op support across node/executor/tests), but there is no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Relevant domain terms ('OpenVINO CPU plugin', 'new operation', 'node registration') are present but lean toward technical jargon; common user-facing variations or synonyms are missing.

3 / 5

Distinctiveness Conflict Risk

The narrow niche of OpenVINO CPU plugin op implementation with specific ISA targets makes it highly distinct with minimal conflict risk against unrelated skills.

5 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
openvinotoolkit/openvino
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.